Architecture for DRAM control optimization using simultaneous bidirectional memory interfaces
A computing device performs both read/write operations concurrently to a memory. Queues for read or write operations are maintained on the memory, allowing the computing device to issue concurrent read/write commands, without complex ordering/buffering circuitry. For a read operation, the memory receives the read command and buffers it in a priority order assigned thereto. The memory can perform the read command and respond with the requested response on a data bus disposed to communicate read data. For a write operation, the memory receives the write command and buffers it for processing in a priority order for that command, such as for relatively immediate processing. The memory can perform the write command using write data on a separate data bus disposed to communication write data.
1. An apparatus including:
a memory device;
a computing device configured to issue a read command and a write command to the memory device via a non-transitory command/address link;
wherein the memory device comprises priority ordering circuitry to associate a priority to the read command and the write command, and configured to reorder execution of the read command and the write command in response to the priority associated with the read command and the write command;
a non-transitory read communication link coupled to the computing device and the memory device, the non-transitory read communication link being configured to transfer read data from the memory device to the computing device in response to the memory device executing the read command;
a non-transitory write communication link coupled to the computing device and the memory device, the non-transitory write communication link being configured to transfer write data associated with the write command from the computing device to the memory device at a same time as and concurrently with the non-transitory read communication link transferring at least a portion of the read data from the memory device to the computing device;
wherein the non-transitory read communication link and the non-transitory write communication link are each configured to operate simultaneously via a single communication path.
2. The apparatus as in claim 1 , wherein:
the non-transitory read communication link and the non-transitory write communication link are free from any latency timing constraint to communicate the read data and the write data between the memory device and the computing device.
3. The apparatus as in claim 1 , wherein:
the memory device comprises a dynamic random access memory (DRAM) device.
4. The apparatus as in claim 1 , wherein:
the memory device includes circuitry to receive the read command from the computing device, to associate a priority order with the read command, to buffer the read command in its associated priority order, and to execute the read command in its associated priority order.
5. The apparatus as in claim 1 , wherein:
the memory device includes circuitry, after receiving a set of read commands directed to a set of multiple memory banks from the computing device, to associate a priority order with those read commands so as to execute the set of read commands with respect to the set of multiple memory banks.
6. The apparatus as in claim 5 , wherein:
the memory device includes circuitry to operate without instruction by the computing device.
7. The apparatus as in claim 6 , wherein:
the memory device includes circuitry to reorder memory access operations directed to multiple memory banks based on a number of operations to be performed by each memory bank.
8. The apparatus as in claim 4 , wherein:
the memory device includes circuitry, after receiving a set of read commands from the computing device, to associate a priority order with the set of read commands based on the execution of the set of read commands to a multi-level memory.
9. The apparatus as in claim 4 , wherein:
the memory device includes circuitry, after performing the read command, to couple the read data to the non-transitory read communication link.
10. The apparatus as in claim 8 , wherein:
the memory device is configured to associate the priority order to a pending write command to be performed before a pending read command;
whereby the pending write command issued by the computing device is performed before the pending read command issued by the computing device.
11. The apparatus as in claim 1 , wherein:
the memory device is configured to receive the write command from the computing device, to associate a priority order with the write command, to buffer the write command in its associated priority order, and to execute the write command in its associated priority order.
12. The apparatus as in claim 1 , wherein:
the computing device includes one or more of:
an application-specific integrated circuit (ASIC), a processor, a system on a chip, or a field-programmable gate array (FPGA).
13. A method comprising:
by a computing device, coupling a read command and a write commands to a non-transitory command/address communication link, and receiving read data from a memory device on a non-transitory read communication link in response to the read command, and coupling write data associated with the write command to the memory device on a non-transitory write communication link;
by the non-transitory read communication link, communicating the read data from the memory device to the computing device;
by the non-transitory write communication link, communicating the write data from the computing device from the computing device to the memory device at a same time as and concurrently with the non-transitory read communication link communicating the read data from the memory device to the computing device;
operating the non-transitory read communication link and the non-transitory write communication link to communicate the read data and the write data concurrently and simultaneously via a single communication path; and
by a memory device, receiving a read command from the computing device, associating a priority order with the read command, buffering the read command in its associated priority order, and performing the read command in its associated priority order.
14. The method as in claim 13 , including:
by the memory device, after receiving a set of second read commands from the computing device, associating a priority order with the set of second read commands based on execution of the set of second read commands by a set of multiple memory banks.
15. The method as in claim 14 , including:
by the memory device, after receiving the set of second read commands from the computing device, associating a priority order with the set of second read commands based on execution of the set of second read commands by a multi-level memory.
16. The method as in claim 15 , including:
by the memory device, associating the priority order of a pending write command to be performed before a pending read command;
wherein the pending write command issued by the computing device is performed before the pending read command issued by the computing device.
17. The method as in claim 13 , including:
by the memory device, receiving a write command from the computing device, associating a priority order with the write command, buffering the write command in its associated priority order, and executing the write command in its associated priority order.